*1️⃣ Import Libraries*

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import warnings

from sklearn.manifold import TSNE
from sklearn.decomposition import PCA
from sklearn.model_selection import train_test_split

import cv2
import random
import os
from PIL import Image
from tqdm import tqdm
import shutil

# Ignore all warnings
warnings.filterwarnings("ignore")

*2️⃣ Directories*

# Define paths
base_dir = "data"
raw_uppercase_dir = os.path.join(base_dir, "raw/UPPER_CASE")
raw_lowercase_dir = os.path.join(base_dir, "raw/lower_case")

balance_uppercase_dir = os.path.join(base_dir, "balance/UPPER_CASE")
balance_lowercase_dir = os.path.join(base_dir, "balance/lower_case")

aug_uppercase_dir = os.path.join(base_dir, "augmentation/UPPER_CASE")
aug_lowercase_dir = os.path.join(base_dir, "augmentation/lower_case")

split_dir = os.path.join(base_dir, "split")

split_train_dir = os.path.join(split_dir, "train")
split_test_dir = os.path.join(split_dir, "test")
split_val_dir = os.path.join(split_dir, "val")

# Create balance directories if they don't exist
os.makedirs(balance_uppercase_dir, exist_ok=True)
os.makedirs(balance_lowercase_dir, exist_ok=True)

os.makedirs(aug_uppercase_dir, exist_ok=True)
os.makedirs(aug_lowercase_dir, exist_ok=True)

os.makedirs(split_uppercase_dir, exist_ok=True)
os.makedirs(split_lowercase_dir, exist_ok=True)

os.makedirs(split_train_dir, exist_ok=True)
os.makedirs(split_test_dir, exist_ok=True)
os.makedirs(split_val_dir, exist_ok=True)

*3️⃣ Image Loading*

# Initialize lists to store images and labels
uppercase_images = []
uppercase_labels = []
lowercase_images = []
lowercase_labels = []

# Load uppercase images
for folder in os.listdir(raw_uppercase_dir):
    folder_path = os.path.join(raw_uppercase_dir, folder)
    if os.path.isdir(folder_path):
        for filename in tqdm(os.listdir(folder_path), desc=f"Loading {folder}...."):
            if filename.endswith(".png"):
                img_path = os.path.join(folder_path, filename)
                try:
                    img = Image.open(img_path)
                    img_array = np.array(img)
                    uppercase_images.append(img_array)
                    uppercase_labels.append(folder)
                except Exception as e:
                    print(f"Error loading image: {img_path}, Error: {e}")

Loading A....: 100%|████████████████████████████████████████████████████████████████| 150/150 [00:00<00:00, 212.86it/s]
Loading B....: 100%|████████████████████████████████████████████████████████████████| 140/140 [00:00<00:00, 156.88it/s]
Loading C....: 100%|████████████████████████████████████████████████████████████████| 101/101 [00:00<00:00, 141.12it/s]
Loading D....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 157.45it/s]
Loading E....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 157.18it/s]
Loading F....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 140.87it/s]
Loading G....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 120.82it/s]
Loading H....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 147.21it/s]
Loading I....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 161.30it/s]
Loading J....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 169.23it/s]
Loading K....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 146.08it/s]
Loading L....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 186.19it/s]
Loading M....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 171.19it/s]
Loading N....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 145.22it/s]
Loading O....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 133.47it/s]
Loading P....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 175.47it/s]
Loading Q....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 194.36it/s]
Loading R....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 156.48it/s]
Loading S....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 169.54it/s]
Loading T....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 131.47it/s]
Loading U....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 145.92it/s]
Loading V....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 158.70it/s]
Loading W....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 117.63it/s]
Loading X....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 114.26it/s]
Loading Y....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 119.39it/s]
Loading Z....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 154.08it/s]

# Load lowercase images
for folder in os.listdir(raw_lowercase_dir):
    folder_path = os.path.join(raw_lowercase_dir, folder)
    if os.path.isdir(folder_path):
        for filename in tqdm(os.listdir(folder_path), desc=f"Loading {folder}...."):
            if filename.endswith(".png"):
                img_path = os.path.join(folder_path, filename)
                try:
                    img = Image.open(img_path)
                    img_array = np.array(img)
                    lowercase_images.append(img_array)
                    lowercase_labels.append(folder)
                except Exception as e:
                    print(f"Error loading image: {img_path}, Error: {e}")

Loading a....: 100%|████████████████████████████████████████████████████████████████| 140/140 [00:00<00:00, 179.94it/s]
Loading b....: 100%|████████████████████████████████████████████████████████████████| 128/128 [00:00<00:00, 162.88it/s]
Loading c....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 138.64it/s]
Loading d....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 155.85it/s]
Loading e....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 113.88it/s]
Loading f....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 129.28it/s]
Loading g....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 108.20it/s]
Loading h....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 173.76it/s]
Loading i....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 143.81it/s]
Loading j....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 142.82it/s]
Loading k....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 142.69it/s]
Loading l....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 120.30it/s]
Loading m....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 135.95it/s]
Loading n....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 121.24it/s]
Loading o....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 148.97it/s]
Loading p....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 106.61it/s]
Loading q....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 125.27it/s]
Loading r....: 100%|████████████████████████████████████████████████████████████████| 200/200 [00:01<00:00, 113.81it/s]
Loading s....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 132.77it/s]
Loading t....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 137.37it/s]
Loading u....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 121.20it/s]
Loading v....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 129.57it/s]
Loading w....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 120.74it/s]
Loading x....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 125.55it/s]
Loading y....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 121.75it/s]
Loading z....: 100%|████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 118.11it/s]

# Get image shapes and lengths
uppercase_image_shape = uppercase_images[0].shape
lowercase_image_shape = lowercase_images[0].shape
uppercase_image_count = len(uppercase_images)
lowercase_image_count = len(lowercase_images)

print(f"Uppercase Image Shape: {uppercase_image_shape}")
print(f"Lowercase Image Shape: {lowercase_image_shape}")
print(f"Number of Uppercase Images: {uppercase_image_count}")
print(f"Number of Lowercase Images: {lowercase_image_count}")

Uppercase Image Shape: (525, 483, 4)
Lowercase Image Shape: (525, 483, 4)
Number of Uppercase Images: 2600
Number of Lowercase Images: 2700

# Display sample uppercase images
plt.figure(figsize=(10, 5))
for i in range(10):
    plt.subplot(2, 5, i+1)
    plt.imshow(uppercase_images[i])
    plt.title(f"Uppercase: {uppercase_labels[i]}")
    plt.axis('off')
plt.suptitle("Sample Uppercase Images")
plt.show()

# Display sample lowercase images
plt.figure(figsize=(10, 5))
for i in range(10):
    plt.subplot(2, 5, i+1)
    plt.imshow(lowercase_images[i])
    plt.title(f"Lowercase: {lowercase_labels[i]}")
    plt.axis('off')
plt.suptitle("Sample Lowercase Images")
plt.show()

# Combine images and labels
all_images = uppercase_images + lowercase_images
all_labels = uppercase_labels + lowercase_labels

# Get unique labels and their counts
unique_labels, label_counts = np.unique(all_labels, return_counts=True)

lower_labels, lower_label_count = np.unique(lowercase_labels, return_counts=True)

# Create a DataFrame to store label counts
lower_label_counts = pd.DataFrame({'Label': lower_labels, 'Count': lower_label_count})

# Sort the DataFrame by Label (A-Z, a-z)
lower_label_counts = lower_label_counts.sort_values(by='Label')

print("Lower Label Counts:")
display(lower_label_counts)

Lower Label Counts:

	Label	Count
0	a	100
1	b	100
2	c	100
3	d	100
4	e	100
5	f	100
6	g	100
7	h	100
8	i	100
9	j	100
10	k	100
11	l	100
12	m	100
13	n	100
14	o	100
15	p	100
16	q	100
17	r	200
18	s	100
19	t	100
20	u	100
21	v	100
22	w	100
23	x	100
24	y	100
25	z	100

upper_labels, upper_label_count = np.unique(uppercase_labels, return_counts=True)

# Create a DataFrame to store label counts
upper_label_counts = pd.DataFrame({'Label': upper_labels, 'Count': upper_label_count})

# Sort the DataFrame by Label (A-Z, a-z)
upper_label_counts = upper_label_counts.sort_values(by='Label')

print("Upper Label Counts:")
display(upper_label_counts)

Upper Label Counts:

	Label	Count
0	A	100
1	B	100
2	C	100
3	D	100
4	E	100
5	F	100
6	G	100
7	H	100
8	I	100
9	J	100
10	K	100
11	L	100
12	M	100
13	N	100
14	O	100
15	P	100
16	Q	100
17	R	100
18	S	100
19	T	100
20	U	100
21	V	100
22	W	100
23	X	100
24	Y	100
25	Z	100

# Create a DataFrame to store label counts
label_counts_df = pd.DataFrame({'Label': unique_labels, 'Count': label_counts})

# Sort the DataFrame by Label (A-Z, a-z)
label_counts_df = label_counts_df.sort_values(by='Label')

print("Label Counts:")
display(label_counts_df)

Label Counts:

	Label	Count
0	A	100
1	B	100
2	C	100
3	D	100
4	E	100
5	F	100
6	G	100
7	H	100
8	I	100
9	J	100
10	K	100
11	L	100
12	M	100
13	N	100
14	O	100
15	P	100
16	Q	100
17	R	100
18	S	100
19	T	100
20	U	100
21	V	100
22	W	100
23	X	100
24	Y	100
25	Z	100
26	a	100
27	b	100
28	c	100
29	d	100
30	e	100
31	f	100
32	g	100
33	h	100
34	i	100
35	j	100
36	k	100
37	l	100
38	m	100
39	n	100
40	o	100
41	p	100
42	q	100
43	r	200
44	s	100
45	t	100
46	u	100
47	v	100
48	w	100
49	x	100
50	y	100
51	z	100

# Visualize the number of images per class
plt.figure(figsize=(12, 6))
plt.bar(lower_label_counts['Label'], lower_label_counts['Count'], color='skyblue')
plt.xlabel("Labels")
plt.ylabel("Number of Images")
plt.title("Number of Images per Class")
plt.xticks(rotation=45)
plt.grid(axis='y', linestyle='--', alpha=0.7)
plt.show()

# Visualize the number of images per class
plt.figure(figsize=(12, 6))
plt.bar(upper_label_counts['Label'], upper_label_counts['Count'], color='skyblue')
plt.xlabel("Uppercase Labels")
plt.ylabel("Number of Images")
plt.title("Number of Images per Class")
plt.xticks(rotation=45)
plt.grid(axis='y', linestyle='--', alpha=0.7)
plt.show()

# Visualize the number of images per class
plt.figure(figsize=(12, 6))
plt.bar(label_counts_df['Label'], label_counts_df['Count'], color='skyblue')
plt.xlabel("Labels")
plt.ylabel("Number of Images")
plt.title("Number of Images per Class")
plt.xticks(rotation=45)
plt.grid(axis='y', linestyle='--', alpha=0.7)
plt.show()

# Pie chart for distribution of images per class
plt.figure(figsize=(18, 18))
plt.pie(upper_label_count, labels=upper_labels, autopct='%1.1f%%', startangle=90, colors=plt.cm.tab20.colors)
plt.title("Distribution of Images per Class")
plt.show()

# Pie chart for distribution of images per class
plt.figure(figsize=(18, 18))
plt.pie(lower_label_count, labels=lower_labels, autopct='%1.1f%%', startangle=90, colors=plt.cm.tab20.colors)
plt.title("Distribution of Images per Class")
plt.show()

# Pie chart for distribution of images per class
plt.figure(figsize=(18, 18))
plt.pie(label_counts, labels=unique_labels, autopct='%1.1f%%', startangle=140, colors=plt.cm.tab20.colors)
plt.title("Distribution of Images per Class")
plt.show()

# Histogram of pixel intensities for a sample uppercase image
sample_image = all_images[0]
plt.figure(figsize=(10, 5))
plt.hist(sample_image.ravel(), bins=256, range=(0, 256), color='black')
plt.title("Pixel Intensity Distribution (Sample Image)")
plt.xlabel("Pixel Intensity")
plt.ylabel("Frequency")
plt.grid(linestyle='--', alpha=0.7)
plt.show()

# Histogram of pixel intensities for a sample uppercase image
sample_uppercase_image = uppercase_images[0]
plt.figure(figsize=(10, 5))
plt.hist(sample_uppercase_image.ravel(), bins=256, range=(0, 256), color='black')
plt.title("Pixel Intensity Distribution (Uppercase Sample Image)")
plt.xlabel("Pixel Intensity")
plt.ylabel("Frequency")
plt.grid(linestyle='--', alpha=0.7)
plt.show()

# Histogram of pixel intensities for a sample lowercase image
sample_lowercase_image = lowercase_images[4]
plt.figure(figsize=(10, 5))
plt.hist(sample_lowercase_image.ravel(), bins=256, range=(0, 256), color='black')
plt.title("Pixel Intensity Distribution (Lowercase Sample Image)")
plt.xlabel("Pixel Intensity")
plt.ylabel("Frequency")
plt.grid(linestyle='--', alpha=0.7)
plt.show()

# Function to compute and plot mean and standard deviation of pixel intensities
def plot_pixel_statistics(images, labels, title):
    """
    Computes and plots the mean and standard deviation of pixel intensities for each label.
    """
    unique_labels = np.unique(labels)
    label_means = {label: [] for label in unique_labels}
    label_stds = {label: [] for label in unique_labels}

    for img, label in zip(images, labels):
        label_means[label].append(np.mean(img))
        label_stds[label].append(np.std(img))

    # Compute average mean and std for each label
    avg_means = {label: np.mean(label_means[label]) for label in unique_labels}
    avg_stds = {label: np.mean(label_stds[label]) for label in unique_labels}

    plt.figure(figsize=(12, 6))
    plt.bar(avg_means.keys(), avg_means.values(), color='blue', alpha=0.7, label='Mean')
    plt.bar(avg_stds.keys(), avg_stds.values(), color='red', alpha=0.7, label='Std Dev')
    plt.xlabel("Labels")
    plt.ylabel("Pixel Intensity")
    plt.title(title)
    plt.xticks(rotation=45)
    plt.legend()
    plt.grid(axis='y', linestyle='--', alpha=0.7)
    plt.show()

# Plot pixel statistics for original uppercase and lowercase data
plot_pixel_statistics(uppercase_images, uppercase_labels, "Uppercase Pixel Statistics (Original Data)")

plot_pixel_statistics(lowercase_images, lowercase_labels, "Lowercase Pixel Statistics (Original Data)")

# Interactive label and image display
while True:
    label_input = input("Enter a label (A-Z, a-z) or '#' to quit: ")
    if label_input == '#':
        break
    try:
        label_index = all_labels.index(label_input)
        plt.imshow(all_images[label_index])
        plt.title(f"Label: {label_input}")
        plt.axis('off')
        plt.show()
    except ValueError:
        print("Invalid label. Please enter a valid label (A-Z, a-z) or '#' to quit.")

*4️⃣ Balancing Dataset*

# Function to balance images for each letter
def balance_images(src_dir, dest_dir, target_count=100):
    for letter in os.listdir(src_dir):
        letter_path = os.path.join(src_dir, letter)
        balanced_letter_path = os.path.join(dest_dir, letter)
        os.makedirs(balanced_letter_path, exist_ok=True)

        # List all images in the letter directory
        images = [img for img in tqdm(os.listdir(letter_path),desc=f"Balancing {letter}...") if img.endswith('.png')]

        # Randomly select images if more than target_count
        if len(images) > target_count:
            images_to_copy = random.sample(images, target_count)
        else:
            images_to_copy = images  # Keep all if less than or equal to target_count

        # Copy selected images to balanced directory
        for img in images_to_copy:
            src_img_path = os.path.join(letter_path, img)
            dest_img_path = os.path.join(balanced_letter_path, img)
            shutil.copy(src_img_path, dest_img_path)
    print("Dataset balancing complete!")

# Balance uppercase and lowercase images
balance_images(raw_uppercase_dir, balance_uppercase_dir, target_count=100)
balance_images(raw_lowercase_dir, balance_lowercase_dir, target_count=100)

Balancing A...: 100%|████████████████████████████████████████████████████████████████████████| 150/150 [00:00<?, ?it/s]
Balancing B...: 100%|████████████████████████████████████████████████████████████████████████| 140/140 [00:00<?, ?it/s]
Balancing C...: 100%|████████████████████████████████████████████████████████████████████████| 101/101 [00:00<?, ?it/s]
Balancing D...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing E...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing F...: 100%|█████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 49601.51it/s]
Balancing G...: 100%|█████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 40956.00it/s]
Balancing H...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing I...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing J...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing K...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing L...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing M...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing N...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing O...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing P...: 100%|█████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 65979.30it/s]
Balancing Q...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing R...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing S...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing T...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing U...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing V...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing W...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing X...: 100%|█████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 13120.32it/s]
Balancing Y...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing Z...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]

Dataset balancing complete!

Balancing a...: 100%|████████████████████████████████████████████████████████████████████████| 140/140 [00:00<?, ?it/s]
Balancing b...: 100%|████████████████████████████████████████████████████████████████████████| 128/128 [00:00<?, ?it/s]
Balancing c...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing d...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing e...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing f...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing g...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing h...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing i...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing j...: 100%|█████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 66177.09it/s]
Balancing k...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing l...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing m...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing n...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing o...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing p...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing q...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing r...: 100%|█████████████████████████████████████████████████████████████| 200/200 [00:00<00:00, 27999.36it/s]
Balancing s...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing t...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing u...: 100%|█████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 49176.97it/s]
Balancing v...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing w...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing x...: 100%|█████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 66239.80it/s]
Balancing y...: 100%|████████████████████████████████████████████████████████████████████████| 100/100 [00:00<?, ?it/s]
Balancing z...: 100%|█████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 13252.98it/s]

Dataset balancing complete!

# Function to display random images from each label
def display_random_images(data_dir, title):
    """
    Displays a random image from each label folder in the specified directory.
    """
    labels = sorted(os.listdir(data_dir))
    plt.figure(figsize=(15, 10))
    for i, label in enumerate(labels):
        label_dir = os.path.join(data_dir, label)
        if os.path.isdir(label_dir):
            images = os.listdir(label_dir)
            if images:
                img_path = os.path.join(label_dir, random.choice(images))
                img = Image.open(img_path)
                plt.subplot(5, 6, i+1)
                plt.imshow(img, cmap='gray')
                plt.title(label)
                plt.axis('off')
    plt.suptitle(title)
    plt.show()

# Display random images for uppercase
display_random_images(balance_uppercase_dir, "Random Uppercase Images (Balance)")

# Display random images for uppercase
display_random_images(balance_lowercase_dir, "Random Uppercase Images (Balance)")

# Initialize lists to store images and labels
balance_uppercase_img = []
balance_uppercase_labels = []
balance_lowercase_img = []
balance_lowercase_labels = []

# Load uppercase images
for folder in os.listdir(balance_uppercase_dir):
    folder_path = os.path.join(balance_uppercase_dir, folder)
    if os.path.isdir(folder_path):
        for filename in tqdm(os.listdir(folder_path), desc=f"Loading {folder}...."):
            if filename.endswith(".png"):
                img_path = os.path.join(folder_path, filename)
                try:
                    img = Image.open(img_path)
                    img_array = np.array(img)
                    balance_uppercase_img.append(img_array)
                    balance_uppercase_labels.append(folder)
                except Exception as e:
                    print(f"Error loading image: {img_path}, Error: {e}")

Loading A....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 41.88it/s]
Loading B....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 46.17it/s]
Loading C....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 61.25it/s]
Loading D....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 56.94it/s]
Loading E....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 50.95it/s]
Loading F....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 49.47it/s]
Loading G....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 53.07it/s]
Loading H....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 51.38it/s]
Loading I....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 51.72it/s]
Loading J....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 41.22it/s]
Loading K....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 45.11it/s]
Loading L....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 44.75it/s]
Loading M....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 50.18it/s]
Loading N....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 59.46it/s]
Loading O....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 51.68it/s]
Loading P....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 48.02it/s]
Loading Q....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 42.25it/s]
Loading R....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 41.40it/s]
Loading S....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 45.50it/s]
Loading T....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 59.07it/s]
Loading U....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 59.55it/s]
Loading V....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 57.93it/s]
Loading W....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 54.89it/s]
Loading X....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 52.49it/s]
Loading Y....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 55.50it/s]
Loading Z....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 56.25it/s]

# Load uppercase images
for folder in os.listdir(balance_lowercase_dir):
    folder_path = os.path.join(balance_lowercase_dir, folder)
    if os.path.isdir(folder_path):
        for filename in tqdm(os.listdir(folder_path), desc=f"Loading {folder}...."):
            if filename.endswith(".png"):
                img_path = os.path.join(folder_path, filename)
                try:
                    img = Image.open(img_path)
                    img_array = np.array(img)
                    balance_lowercase_img.append(img_array)
                    balance_lowercase_labels.append(folder)
                except Exception as e:
                    print(f"Error loading image: {img_path}, Error: {e}")

Loading a....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 61.04it/s]
Loading b....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 57.86it/s]
Loading c....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 54.73it/s]
Loading d....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 49.34it/s]
Loading e....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 49.59it/s]
Loading f....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 47.44it/s]
Loading g....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 46.57it/s]
Loading h....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 51.82it/s]
Loading i....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 66.47it/s]
Loading j....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 49.08it/s]
Loading k....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 40.57it/s]
Loading l....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 41.17it/s]
Loading m....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 52.15it/s]
Loading n....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 48.03it/s]
Loading o....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 54.65it/s]
Loading p....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 66.30it/s]
Loading q....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 47.37it/s]
Loading r....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 42.55it/s]
Loading s....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 54.47it/s]
Loading t....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 59.38it/s]
Loading u....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 62.78it/s]
Loading v....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:02<00:00, 42.36it/s]
Loading w....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 55.71it/s]
Loading x....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 52.42it/s]
Loading y....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 53.74it/s]
Loading z....: 100%|█████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 55.51it/s]

# Get image shapes and lengths
balance_uppercase_img_shape = balance_uppercase_img[0].shape
balance_lowercase_img_shape = balance_lowercase_img[0].shape
balance_uppercase_img_count = len(balance_uppercase_img)
balance_lowercase_count = len(balance_lowercase_img)

print(f"Uppercase Image Shape: {balance_uppercase_img_shape}")
print(f"Lowercase Image Shape: {lowercase_image_shape}")
print(f"Number of Uppercase Images: {balance_uppercase_img_count}")
print(f"Number of Lowercase Images: {balance_lowercase_count}")

Uppercase Image Shape: (525, 483, 4)
Lowercase Image Shape: (525, 483, 4)
Number of Uppercase Images: 2600
Number of Lowercase Images: 2600

balance_img = balance_uppercase_img + balance_lowercase_img
balance_labels = balance_uppercase_labels + balance_lowercase_labels

# Get unique labels and their counts
blance_img_labels, balance_img_count = np.unique(balance_labels, return_counts=True)
balance_uppercase_img_labels, balance_uppercase_img_count = np.unique(balance_uppercase_labels, return_counts=True)
balance_lowercase_img_labels, balance_lowercase_img_count = np.unique(balance_lowercase_labels, return_counts=True)

# Create a DataFrame to store label counts
balance_upper_label_counts= pd.DataFrame({'Label': balance_uppercase_img_labels, 'Count': balance_uppercase_img_count})

# Sort the DataFrame by Label (A-Z, a-z)
balance_upper_label_counts= balance_upper_label_counts.sort_values(by='Label')

print("Label Counts:")
display(balance_upper_label_counts)

Label Counts:

	Label	Count
0	A	100
1	B	100
2	C	100
3	D	100
4	E	100
5	F	100
6	G	100
7	H	100
8	I	100
9	J	100
10	K	100
11	L	100
12	M	100
13	N	100
14	O	100
15	P	100
16	Q	100
17	R	100
18	S	100
19	T	100
20	U	100
21	V	100
22	W	100
23	X	100
24	Y	100
25	Z	100

# Visualize the number of images per class
plt.figure(figsize=(12, 6))
plt.bar(balance_upper_label_counts['Label'], balance_upper_label_counts['Count'], color='skyblue')
plt.xlabel("Labels")
plt.ylabel("Number of Images")
plt.title("Number of Images per Class")
plt.xticks(rotation=45)
plt.grid(axis='y', linestyle='--', alpha=0.7)
plt.show()

# Pie chart for distribution of images per class
plt.figure(figsize=(18, 18))
plt.pie(balance_uppercase_img_count, labels=balance_uppercase_img_labels, autopct='%1.f%%', startangle=140, colors=plt.cm.tab20.colors)
plt.title("Distribution of Images per Class")
plt.show()

# Create a DataFrame to store label counts
balance_lower_label_counts= pd.DataFrame({'Label': balance_lowercase_img_labels, 'Count': balance_lowercase_img_count})

# Sort the DataFrame by Label (A-Z, a-z)
balance_lower_label_counts= balance_lower_label_counts.sort_values(by='Label')

print("Label Counts:")
display(balance_lower_label_counts)

Label Counts:

	Label	Count
0	a	100
1	b	100
2	c	100
3	d	100
4	e	100
5	f	100
6	g	100
7	h	100
8	i	100
9	j	100
10	k	100
11	l	100
12	m	100
13	n	100
14	o	100
15	p	100
16	q	100
17	r	100
18	s	100
19	t	100
20	u	100
21	v	100
22	w	100
23	x	100
24	y	100
25	z	100

# Visualize the number of images per class
plt.figure(figsize=(12, 6))
plt.bar(balance_lower_label_counts['Label'], balance_lower_label_counts['Count'], color='skyblue')
plt.xlabel("Labels")
plt.ylabel("Number of Images")
plt.title("Number of Images per Class")
plt.xticks(rotation=45)
plt.grid(axis='y', linestyle='--', alpha=0.7)
plt.show()

# Pie chart for distribution of images per class
plt.figure(figsize=(18, 18))
plt.pie(balance_lowercase_img_count, labels=balance_lowercase_img_labels, autopct='%1.f%%', startangle=140, colors=plt.cm.tab20.colors)
plt.title("Distribution of Images per Class")
plt.show()

# Create a DataFrame to store label counts
balance_label_counts= pd.DataFrame({'Label': blance_img_labels, 'Count': balance_img_count})

# Sort the DataFrame by Label (A-Z, a-z)
balance_label_counts= balance_label_counts.sort_values(by='Label')

print("Label Counts:")
display(balance_label_counts)

Label Counts:

	Label	Count
0	A	100
1	B	100
2	C	100
3	D	100
4	E	100
5	F	100
6	G	100
7	H	100
8	I	100
9	J	100
10	K	100
11	L	100
12	M	100
13	N	100
14	O	100
15	P	100
16	Q	100
17	R	100
18	S	100
19	T	100
20	U	100
21	V	100
22	W	100
23	X	100
24	Y	100
25	Z	100
26	a	100
27	b	100
28	c	100
29	d	100
30	e	100
31	f	100
32	g	100
33	h	100
34	i	100
35	j	100
36	k	100
37	l	100
38	m	100
39	n	100
40	o	100
41	p	100
42	q	100
43	r	100
44	s	100
45	t	100
46	u	100
47	v	100
48	w	100
49	x	100
50	y	100
51	z	100

# Visualize the number of images per class
plt.figure(figsize=(12, 6))
plt.bar(balance_label_counts['Label'], balance_label_counts['Count'], color='skyblue')
plt.xlabel("Labels")
plt.ylabel("Number of Images")
plt.title("Number of Images per Class")
plt.xticks(rotation=45)
plt.grid(axis='y', linestyle='--', alpha=0.7)
plt.show()

# Pie chart for distribution of images per class
plt.figure(figsize=(18, 18))
plt.pie(balance_img_count, labels=blance_img_labels, autopct='%1.f%%', startangle=140, colors=plt.cm.tab20.colors)
plt.title("Distribution of Images per Class")
plt.show()

*5️⃣ Preprocessing*

# Define preprocessing parameters
target_size = (28, 28)  # Resize images to 28x28
normalize = True        # Normalize pixel values to [0, 1]
augment = True          # Apply data augmentation

# Define augmentation parameters
rotation_range = (-10, 10)  # Rotate images by ±10 degrees
translation_range = (-5, 5) # Translate images by ±5 pixels
scale_range = (0.9, 1.1)    # Scale images by 90% to 110%

# Function to apply augmentation
def augment_image(img):
    """
    Applies random augmentation to an image.
    """
    # Rotation
    angle = random.uniform(rotation_range[0], rotation_range[1])
    rows, cols = img.shape[:2]
    M = cv2.getRotationMatrix2D((cols/2, rows/2), angle, 1)
    img = cv2.warpAffine(img, M, (cols, rows))

    # Translation
    tx = random.uniform(translation_range[0], translation_range[1])
    ty = random.uniform(translation_range[0], translation_range[1])
    M = np.float32([[1, 0, tx], [0, 1, ty]])
    img = cv2.warpAffine(img, M, (cols, rows))

    # Scaling
    scale = random.uniform(scale_range[0], scale_range[1])
    img = cv2.resize(img, None, fx=scale, fy=scale)
    img = cv2.resize(img, target_size)  # Resize back to target size

    return img

# Preprocess and save uppercase images
for folder in os.listdir(balance_uppercase_dir):
    folder_path = os.path.join(balance_uppercase_dir, folder)
    if os.path.isdir(folder_path):
        # Create corresponding folder in augmentation directory
        aug_folder_path = os.path.join(aug_uppercase_dir, folder)
        os.makedirs(aug_folder_path, exist_ok=True)

        for filename in tqdm(os.listdir(folder_path), desc=f"Processing {folder} Images....."):
            if filename.endswith(".png"):
                img_path = os.path.join(folder_path, filename)
                try:
                    # Load image
                    img = Image.open(img_path)
                    img = img.resize(target_size)  # Resize
                    img = img.convert('L')         # Convert to grayscale
                    img_array = np.array(img)

                    # Normalize
                    if normalize:
                        img_array = img_array / 255.0

                    # Augment
                    if augment:
                        img_array = augment_image(img_array)

                    # Save preprocessed image
                    aug_img_path = os.path.join(aug_folder_path, filename)
                    Image.fromarray((img_array * 255).astype(np.uint8)).save(aug_img_path)

                except Exception as e:
                    print(f"Error processing image: {img_path}, Error: {e}")

Processing A Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 74.33it/s]
Processing B Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 77.61it/s]
Processing C Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 70.95it/s]
Processing D Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 55.09it/s]
Processing E Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 61.72it/s]
Processing F Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 59.85it/s]
Processing G Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 66.86it/s]
Processing H Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 63.02it/s]
Processing I Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 62.36it/s]
Processing J Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 64.83it/s]
Processing K Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 70.24it/s]
Processing L Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 65.33it/s]
Processing M Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 96.00it/s]
Processing N Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 73.92it/s]
Processing O Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 76.32it/s]
Processing P Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 77.40it/s]
Processing Q Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 80.50it/s]
Processing R Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 89.89it/s]
Processing S Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 88.26it/s]
Processing T Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 94.77it/s]
Processing U Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 88.52it/s]
Processing V Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 84.52it/s]
Processing W Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 68.23it/s]
Processing X Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 73.32it/s]
Processing Y Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 71.15it/s]
Processing Z Images.....: 100%|██████████████████████████████████████████████████████| 100/100 [00:01<00:00, 90.57it/s]

# Preprocess and save lowercase images
for folder in os.listdir(balance_lowercase_dir):
    folder_path = os.path.join(balance_lowercase_dir, folder)
    if os.path.isdir(folder_path):
        # Create corresponding folder in augmentation directory
        aug_folder_path = os.path.join(aug_lowercase_dir, folder)
        os.makedirs(aug_folder_path, exist_ok=True)

        for filename in tqdm(os.listdir(folder_path), desc=f"Processing {folder} Images..."):
            if filename.endswith(".png"):
                img_path = os.path.join(folder_path, filename)
                try:
                    # Load image
                    img = Image.open(img_path)
                    img = img.resize(target_size)  # Resize
                    img = img.convert('L')         # Convert to grayscale
                    img_array = np.array(img)

                    # Normalize
                    if normalize:
                        img_array = img_array / 255.0

                    # Augment
                    if augment:
                        img_array = augment_image(img_array)

                    # Save preprocessed image
                    aug_img_path = os.path.join(aug_folder_path, filename)
                    Image.fromarray((img_array * 255).astype(np.uint8)).save(aug_img_path)

                except Exception as e:
                    print(f"Error processing image: {img_path}, Error: {e}")

Processing a Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 86.60it/s]
Processing b Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 74.42it/s]
Processing c Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 73.87it/s]
Processing d Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 73.01it/s]
Processing e Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 66.21it/s]
Processing f Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 74.06it/s]
Processing g Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 83.05it/s]
Processing h Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 96.19it/s]
Processing i Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 95.81it/s]
Processing j Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 85.03it/s]
Processing k Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 88.22it/s]
Processing l Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 92.75it/s]
Processing m Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 96.78it/s]
Processing n Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 92.59it/s]
Processing o Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 76.81it/s]
Processing p Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 80.93it/s]
Processing q Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 90.88it/s]
Processing r Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 82.87it/s]
Processing s Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 86.47it/s]
Processing t Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 67.30it/s]
Processing u Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 75.80it/s]
Processing v Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 92.03it/s]
Processing w Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 73.30it/s]
Processing x Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 69.31it/s]
Processing y Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 70.82it/s]
Processing z Images...: 100%|████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 72.02it/s]

# Function to display random images from each label
def display_random_images(data_dir, title):
    """
    Displays a random image from each label folder in the specified directory.
    """
    labels = sorted(os.listdir(data_dir))
    plt.figure(figsize=(15, 10))
    for i, label in enumerate(labels):
        label_dir = os.path.join(data_dir, label)
        if os.path.isdir(label_dir):
            images = os.listdir(label_dir)
            if images:
                img_path = os.path.join(label_dir, random.choice(images))
                img = Image.open(img_path)
                plt.subplot(5, 6, i+1)
                plt.imshow(img, cmap='gray')
                plt.title(label)
                plt.axis('off')
    plt.suptitle(title)
    plt.show()

# Display random images for uppercase
display_random_images(aug_uppercase_dir, "Random Uppercase Images (Augmented)")

# Display random images for lowercase
display_random_images(aug_lowercase_dir, "Random Lowercase Images (Augmented)")

# Function to display user-defined label and number of images
def display_user_defined_images(raw_dir, aug_dir, label, num_images):
    """
    Displays a user-defined number of images for a specific label from both raw and augmented directories.
    """
    raw_label_dir = os.path.join(raw_dir, label)
    aug_label_dir = os.path.join(aug_dir, label)

    if os.path.isdir(raw_label_dir) and os.path.isdir(aug_label_dir):
        raw_images = os.listdir(raw_label_dir)[:num_images]
        aug_images = os.listdir(aug_label_dir)[:num_images]

        plt.figure(figsize=(15, 5))
        for i, (raw_img_name, aug_img_name) in enumerate(zip(raw_images, aug_images)):
            # Display original image
            raw_img_path = os.path.join(raw_label_dir, raw_img_name)
            raw_img = Image.open(raw_img_path)
            plt.subplot(2, num_images, i+1)
            plt.imshow(raw_img, cmap='gray')
            plt.title(f"Original: {label}")
            plt.axis('off')

            # Display preprocessed image
            aug_img_path = os.path.join(aug_label_dir, aug_img_name)
            aug_img = Image.open(aug_img_path)
            plt.subplot(2, num_images, num_images + i+1)
            plt.imshow(aug_img, cmap='gray')
            plt.title(f"Preprocessed: {label}")
            plt.axis('off')
        plt.suptitle(f"Original vs Preprocessed Images for Label: {label}")
        plt.show()
    else:
        print(f"Label '{label}' not found in both directories.")

# User input for label and number of images
label_input = input("Enter a label (A-Z): ")
num_images_input = int(input("Enter the number of images to display: "))
display_user_defined_images(balance_uppercase_dir, aug_uppercase_dir, label_input.upper(), num_images_input)

# User input for label and number of images
label_input = input("Enter a label (a-z): ")
num_images_input = int(input("Enter the number of images to display: "))
display_user_defined_images(balance_lowercase_dir, aug_lowercase_dir, label_input.lower(), num_images_input)

# Size comparison of original and processed images
def compare_image_sizes(raw_dir, aug_dir, label):
    """
    Compares the sizes of original and preprocessed images for a specific label.
    """
    raw_label_dir = os.path.join(raw_dir, label)
    aug_label_dir = os.path.join(aug_dir, label)

    if os.path.isdir(raw_label_dir) and os.path.isdir(aug_label_dir):
        raw_img_path = os.path.join(raw_label_dir, os.listdir(raw_label_dir)[5])
        aug_img_path = os.path.join(aug_label_dir, os.listdir(aug_label_dir)[5])

        raw_img = Image.open(raw_img_path)
        aug_img = Image.open(aug_img_path)

        print(f"Original Image Size: {raw_img.size}")
        print(f"Preprocessed Image Size: {aug_img.size}")

        plt.figure(figsize=(10, 5))
        plt.subplot(1, 2, 1)
        plt.imshow(raw_img, cmap='gray')
        plt.title(f"Original: {label}")
        plt.axis('off')

        plt.subplot(1, 2, 2)
        plt.imshow(aug_img, cmap='gray')
        plt.title(f"Preprocessed: {label}")
        plt.axis('off')
        plt.suptitle(f"Size Comparison for Label: {label}")
        plt.show()
    else:
        print(f"Label '{label}' not found in both directories.")

# Compare sizes for a sample label
compare_image_sizes(balance_uppercase_dir, aug_uppercase_dir, "A")

Original Image Size: (483, 525)
Preprocessed Image Size: (28, 28)

# Compare sizes for a sample label
compare_image_sizes(balance_lowercase_dir, aug_lowercase_dir, "c")

Original Image Size: (483, 525)
Preprocessed Image Size: (28, 28)

# Histogram of pixel intensities for original and preprocessed images
def plot_pixel_histogram(raw_dir, aug_dir, label):
    """
    Plots histograms of pixel intensities for original and preprocessed images.
    """
    raw_label_dir = os.path.join(raw_dir, label)
    aug_label_dir = os.path.join(aug_dir, label)

    if os.path.isdir(raw_label_dir) and os.path.isdir(aug_label_dir):
        raw_img_path = os.path.join(raw_label_dir, os.listdir(raw_label_dir)[0])
        aug_img_path = os.path.join(aug_label_dir, os.listdir(aug_label_dir)[0])

        raw_img = np.array(Image.open(raw_img_path))
        aug_img = np.array(Image.open(aug_img_path))

        plt.figure(figsize=(15, 4))
        plt.subplot(1, 2, 1)
        plt.hist(raw_img.ravel(), bins=256, range=(0, 256), color='blue', alpha=0.7)
        plt.title(f"Original: {label}")
        plt.xlabel("Pixel Intensity")
        plt.ylabel("Frequency")

        plt.subplot(1, 2, 2)
        plt.hist(aug_img.ravel(), bins=256, range=(0, 256), color='green', alpha=0.7)
        plt.title(f"Preprocessed: {label}")
        plt.xlabel("Pixel Intensity")
        plt.ylabel("Frequency")
        plt.suptitle(f"Pixel Intensity Histograms for Label: {label}")
        plt.show()
    else:
        print(f"Label '{label}' not found in both directories.")

# Plot histograms for a sample label
plot_pixel_histogram(balance_uppercase_dir, aug_uppercase_dir, "A")

# Plot histograms for a sample label
plot_pixel_histogram(balance_lowercase_dir, aug_lowercase_dir, "a")

# Function to display a grid of images for a specific label
def display_label_image_grid(data_dir, label, num_images=25):
    """
    Displays a grid of images for a specific label.
    """
    label_dir = os.path.join(data_dir, label)
    if os.path.isdir(label_dir):
        images = os.listdir(label_dir)
        if images:
            plt.figure(figsize=(10, 10))
            for i in range(min(num_images, len(images))):
                img_path = os.path.join(label_dir, images[i])
                img = Image.open(img_path)
                plt.subplot(5, 5, i+1)
                plt.imshow(img, cmap='gray')
                plt.title(f"Label: {label}")
                plt.axis('off')
            plt.suptitle(f"Image Grid for Label: {label}")
            plt.show()
        else:
            print(f"No images found for label: {label}")
    else:
        print(f"Label '{label}' not found in directory.")

# Display image grid for a specific label
display_label_image_grid(aug_uppercase_dir, "D")

# Display image grid for a specific label
display_label_image_grid(aug_lowercase_dir, "z")

# Function to visualize augmentation effects
def visualize_augmentation_effects(data_dir, label):
    """
    Visualizes the effects of augmentation on a sample image.
    """
    label_dir = os.path.join(data_dir, label)
    if os.path.isdir(label_dir):
        images = os.listdir(label_dir)
        if images:
            img_path = os.path.join(label_dir, images[0])
            img = Image.open(img_path)
            img_array = np.array(img)

            # Apply augmentation
            augmented_img = augment_image(img_array)

            plt.figure(figsize=(10, 5))
            plt.subplot(1, 2, 1)
            plt.imshow(img, cmap='gray')
            plt.title("Processed Image")
            plt.axis('off')

            plt.subplot(1, 2, 2)
            plt.imshow(augmented_img, cmap='gray')
            plt.title("Augmented Image")
            plt.axis('off')
            plt.suptitle(f"Augmentation Effects for Label: {label}")
            plt.show()
        else:
            print(f"No images found for label: {label}")
    else:
        print(f"Label '{label}' not found in directory.")

# Visualize augmentation effects for a sample label
visualize_augmentation_effects(aug_uppercase_dir, "E")

# Visualize augmentation effects for a sample label
visualize_augmentation_effects(aug_lowercase_dir, "f")

# Function to plot class distribution
def plot_class_distribution(data_dir, title):
    """
    Plots the distribution of images across labels.
    """
    label_counts = {}
    for label in os.listdir(data_dir):
        label_dir = os.path.join(data_dir, label)
        if os.path.isdir(label_dir):
            label_counts[label] = len(os.listdir(label_dir))

    plt.figure(figsize=(12, 6))
    plt.bar(label_counts.keys(), label_counts.values(), color='skyblue')
    plt.xlabel("Labels")
    plt.ylabel("Number of Images")
    plt.title(title)
    plt.xticks(rotation=45)
    plt.grid(axis='y', linestyle='--', alpha=0.7)
    plt.show()

# Plot class distribution for uppercase and lowercase
plot_class_distribution(aug_uppercase_dir, "Uppercase Augmented Image Distribution")

plot_class_distribution(aug_lowercase_dir, "Lowercase Augmented Image Distribution")

# Function to compute and plot mean and standard deviation of pixel intensities
def plot_pixel_statistics(data_dir, title):
    """
    Computes and plots the mean and standard deviation of pixel intensities for each label.
    """
    label_means = {}
    label_stds = {}
    for label in os.listdir(data_dir):
        label_dir = os.path.join(data_dir, label)
        if os.path.isdir(label_dir):
            pixel_values = []
            for img_name in os.listdir(label_dir):
                img_path = os.path.join(label_dir, img_name)
                img = Image.open(img_path)
                img_array = np.array(img)
                pixel_values.extend(img_array.flatten())
            label_means[label] = np.mean(pixel_values)
            label_stds[label] = np.std(pixel_values)

    plt.figure(figsize=(12, 6))
    plt.bar(label_means.keys(), label_means.values(), color='blue', alpha=0.7, label='Mean')
    plt.bar(label_stds.keys(), label_stds.values(), color='red', alpha=0.7, label='Std Dev')
    plt.xlabel("Labels")
    plt.ylabel("Pixel Intensity")
    plt.title(title)
    plt.xticks(rotation=45)
    plt.legend()
    plt.grid(axis='y', linestyle='--', alpha=0.7)
    plt.show()

# Plot pixel statistics for uppercase and lowercase
plot_pixel_statistics(aug_uppercase_dir, "Uppercase Pixel Statistics")

plot_pixel_statistics(aug_lowercase_dir, "Lowercase Pixel Statistics")

# Function to visualize t-SNE or PCA
def visualize_dimensionality_reduction(data_dir, title, method='tsne'):
    """
    Visualizes the high-dimensional image data in 2D using t-SNE or PCA.
    """
    images = []
    labels = []
    for label in os.listdir(data_dir):
        label_dir = os.path.join(data_dir, label)
        if os.path.isdir(label_dir):
            for img_name in os.listdir(label_dir):
                img_path = os.path.join(label_dir, img_name)
                img = Image.open(img_path)
                img_array = np.array(img).flatten()
                images.append(img_array)
                labels.append(label)

    images = np.array(images)
    labels = np.array(labels)

    if method == 'tsne':
        tsne = TSNE(n_components=2, random_state=42)
        reduced_data = tsne.fit_transform(images)
    elif method == 'pca':
        pca = PCA(n_components=2)
        reduced_data = pca.fit_transform(images)

    plt.figure(figsize=(10, 8))
    scatter = plt.scatter(reduced_data[:, 0], reduced_data[:, 1], cmap='tab20', alpha=0.7)
    plt.xlabel("Component 1")
    plt.ylabel("Component 2")
    plt.title(title)
    plt.legend(*scatter.legend_elements(), title="Labels")
    plt.show()

# Visualize t-SNE for uppercase and lowercase
visualize_dimensionality_reduction(aug_uppercase_dir, "t-SNE Visualization for Uppercase", method='tsne')

visualize_dimensionality_reduction(aug_lowercase_dir, "t-SNE Visualization for Lowercase", method='tsne')

visualize_dimensionality_reduction(aug_uppercase_dir, "PCA Visualization for Uppercase", method='pca')

visualize_dimensionality_reduction(aug_lowercase_dir, "PCA Visualization for Uppercase", method='pca')

*6️⃣ Image splliting*

for split in ["train", "test", "val"]:
    for case in ["uppercase", "lowercase"]:
        char_range = "ABCDEFGHIJKLMNOPQRSTUVWXYZ" if case == "uppercase" else "abcdefghijklmnopqrstuvwxyz"
        for char in char_range:
            target_dir = os.path.join(split_dir, split, case, char)
            os.makedirs(target_dir, exist_ok=True)  # Create if it doesn't exist

            # Clear existing files (if any)
            for filename in os.listdir(target_dir):
                file_path = os.path.join(target_dir, filename)
                try:
                    if os.path.isfile(file_path):
                        os.remove(file_path)
                    elif os.path.isdir(file_path): # Handle subdirectories if any
                        shutil.rmtree(file_path)
                except Exception as e: # Catch potential errors and print them
                    print(f"Error deleting {file_path}: {e}")

# Function to load and limit images to 100 per label
def load_and_limit_images(data_dir, label, limit=100):
    """
    Loads images for a specific label and limits the number to a specified limit.
    """
    label_dir = os.path.join(data_dir, label)
    if os.path.isdir(label_dir):
        images = [img for img in os.listdir(label_dir) if img.endswith(".png")]
        if len(images) > limit:
            images = random.sample(images, limit)
        return images
    return []

def split_and_copy_data(source_dir, dest_dir, split_ratio=(0.7, 0.15, 0.15)):
    for case in ["uppercase", "lowercase"]:
        char_range = "ABCDEFGHIJKLMNOPQRSTUVWXYZ" if case == "uppercase" else "abcdefghijklmnopqrstuvwxyz"
        for char in tqdm(char_range, desc=f"Splitting {case}"):
            images = load_and_limit_images(source_dir if case == "uppercase" else source_dir.replace("UPPER","lower"), char) # Dynamic source dir
            if not images: # Skip if no images are found for the character.
                continue
            random.shuffle(images)

            train_len = int(len(images) * split_ratio[0])
            val_len = int(len(images) * split_ratio[1])

            train_images = images[:train_len]
            val_images = images[train_len:train_len + val_len]
            test_images = images[train_len + val_len:]

            for split, image_list in [("train", train_images), ("val", val_images), ("test", test_images)]:
                target_dir = os.path.join(dest_dir, split, case, char)
                for image_name in tqdm(image_list, desc=f"Copying {split} images for {char}", leave=False):
                    source_path = os.path.join(source_dir if case == "uppercase" else source_dir.replace("UPPER","lower"), char, image_name)
                    target_path = os.path.join(target_dir, image_name)
                    shutil.copy(source_path, target_path)

# Example usage (T-2 split):
split_and_copy_data(aug_uppercase_dir, split_dir)

Splitting uppercase:   0%|                                                                      | 0/26 [00:00<?, ?it/s]
Copying train images for A:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for A:   4%|██▎                                                    | 3/70 [00:00<00:02, 26.78it/s]
Copying train images for A:  51%|███████████████████████████▎                         | 36/70 [00:00<00:00, 193.78it/s]
                                                                                                                       
Copying val images for A:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for A:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:   4%|██▍                                                           | 1/26 [00:00<00:11,  2.26it/s]
Copying train images for B:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for B:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for B:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:   8%|████▊                                                         | 2/26 [00:00<00:06,  3.61it/s]
Copying train images for C:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for C:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for C:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  12%|███████▏                                                      | 3/26 [00:00<00:05,  4.50it/s]
Copying train images for D:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for D:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for D:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  15%|█████████▌                                                    | 4/26 [00:00<00:04,  5.20it/s]
Copying train images for E:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for E:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for E:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  19%|███████████▉                                                  | 5/26 [00:01<00:03,  5.78it/s]
Copying train images for F:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for F:  93%|█████████████████████████████████████████████████▏   | 65/70 [00:00<00:00, 646.03it/s]
                                                                                                                       
Copying val images for F:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for F:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  23%|██████████████▎                                               | 6/26 [00:01<00:03,  5.81it/s]
Copying train images for G:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for G:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for G:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  27%|████████████████▋                                             | 7/26 [00:01<00:03,  6.24it/s]
Copying train images for H:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for H:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for H:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  31%|███████████████████                                           | 8/26 [00:01<00:02,  6.64it/s]
Copying train images for I:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for I:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for I:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  35%|█████████████████████▍                                        | 9/26 [00:01<00:02,  6.88it/s]
Copying train images for J:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for J:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for J:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  38%|███████████████████████▍                                     | 10/26 [00:01<00:02,  7.07it/s]
Copying train images for K:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for K:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for K:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  42%|█████████████████████████▊                                   | 11/26 [00:01<00:02,  6.95it/s]
Copying train images for L:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for L:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for L:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  46%|████████████████████████████▏                                | 12/26 [00:02<00:01,  7.25it/s]
Copying train images for M:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for M:  99%|████████████████████████████████████████████████████▏| 69/70 [00:00<00:00, 677.74it/s]
                                                                                                                       
Copying val images for M:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for M:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  50%|██████████████████████████████▌                              | 13/26 [00:02<00:01,  6.86it/s]
Copying train images for N:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for N:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for N:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  54%|████████████████████████████████▊                            | 14/26 [00:02<00:01,  6.80it/s]
Copying train images for O:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for O:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for O:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  58%|███████████████████████████████████▏                         | 15/26 [00:02<00:01,  6.76it/s]
Copying train images for P:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for P:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for P:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  62%|█████████████████████████████████████▌                       | 16/26 [00:02<00:01,  6.93it/s]
Copying train images for Q:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for Q:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for Q:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  65%|███████████████████████████████████████▉                     | 17/26 [00:02<00:01,  6.91it/s]
Copying train images for R:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for R:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for R:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  69%|██████████████████████████████████████████▏                  | 18/26 [00:02<00:01,  6.46it/s]
Copying train images for S:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for S:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for S:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  73%|████████████████████████████████████████████▌                | 19/26 [00:03<00:01,  6.52it/s]
Copying train images for T:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for T:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for T:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  77%|██████████████████████████████████████████████▉              | 20/26 [00:03<00:00,  6.77it/s]
Copying train images for U:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for U:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for U:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  81%|█████████████████████████████████████████████████▎           | 21/26 [00:03<00:00,  6.85it/s]
Copying train images for V:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for V:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for V:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  85%|███████████████████████████████████████████████████▌         | 22/26 [00:03<00:00,  6.85it/s]
Copying train images for W:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for W:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for W:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  88%|█████████████████████████████████████████████████████▉       | 23/26 [00:03<00:00,  6.83it/s]
Copying train images for X:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for X:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for X:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Copying test images for X:  87%|██████████████████████████████████████████████▊       | 13/15 [00:00<00:00, 127.17it/s]
Splitting uppercase:  92%|████████████████████████████████████████████████████████▎    | 24/26 [00:03<00:00,  5.48it/s]
Copying train images for Y:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for Y:  64%|██████████████████████████████████                   | 45/70 [00:00<00:00, 423.44it/s]
                                                                                                                       
Copying val images for Y:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for Y:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase:  96%|██████████████████████████████████████████████████████████▋  | 25/26 [00:04<00:00,  4.65it/s]
Copying train images for Z:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for Z:  94%|█████████████████████████████████████████████████▉   | 66/70 [00:00<00:00, 658.72it/s]
                                                                                                                       
Copying val images for Z:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for Z:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting uppercase: 100%|█████████████████████████████████████████████████████████████| 26/26 [00:04<00:00,  5.91it/s]
Splitting lowercase:   0%|                                                                      | 0/26 [00:00<?, ?it/s]
Copying train images for a:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for a:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for a:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:   4%|██▍                                                           | 1/26 [00:00<00:03,  7.04it/s]
Copying train images for b:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for b:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for b:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:   8%|████▊                                                         | 2/26 [00:00<00:03,  7.30it/s]
Copying train images for c:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for c:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for c:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  12%|███████▏                                                      | 3/26 [00:00<00:03,  6.97it/s]
Copying train images for d:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for d:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for d:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  15%|█████████▌                                                    | 4/26 [00:00<00:03,  6.80it/s]
Copying train images for e:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for e:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for e:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  19%|███████████▉                                                  | 5/26 [00:00<00:02,  7.12it/s]
Copying train images for f:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for f:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for f:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  23%|██████████████▎                                               | 6/26 [00:00<00:02,  7.30it/s]
Copying train images for g:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for g:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for g:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  27%|████████████████▋                                             | 7/26 [00:00<00:02,  7.53it/s]
Copying train images for h:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for h:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for h:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  31%|███████████████████                                           | 8/26 [00:01<00:02,  7.74it/s]
Copying train images for i:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for i:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for i:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  35%|█████████████████████▍                                        | 9/26 [00:01<00:02,  7.90it/s]
Copying train images for j:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for j:  39%|████████████████████▍                                | 27/70 [00:00<00:00, 155.78it/s]
Copying train images for j:  89%|██████████████████████████████████████████████▉      | 62/70 [00:00<00:00, 237.18it/s]
                                                                                                                       
Copying val images for j:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for j:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  38%|███████████████████████▍                                     | 10/26 [00:01<00:03,  4.62it/s]
Copying train images for k:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for k:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for k:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  42%|█████████████████████████▊                                   | 11/26 [00:01<00:03,  4.85it/s]
Copying train images for l:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for l:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for l:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  46%|████████████████████████████▏                                | 12/26 [00:01<00:02,  5.14it/s]
Copying train images for m:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for m:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for m:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  50%|██████████████████████████████▌                              | 13/26 [00:02<00:02,  5.24it/s]
Copying train images for n:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for n:  84%|████████████████████████████████████████████▋        | 59/70 [00:00<00:00, 549.58it/s]
                                                                                                                       
Copying val images for n:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for n:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  54%|████████████████████████████████▊                            | 14/26 [00:02<00:02,  5.21it/s]
Copying train images for o:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for o:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for o:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  58%|███████████████████████████████████▏                         | 15/26 [00:02<00:02,  5.43it/s]
Copying train images for p:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for p:  80%|██████████████████████████████████████████▍          | 56/70 [00:00<00:00, 550.46it/s]
                                                                                                                       
Copying val images for p:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for p:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  62%|█████████████████████████████████████▌                       | 16/26 [00:02<00:01,  5.15it/s]
Copying train images for q:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for q:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for q:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  65%|███████████████████████████████████████▉                     | 17/26 [00:02<00:01,  5.24it/s]
Copying train images for r:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for r:  90%|███████████████████████████████████████████████▋     | 63/70 [00:00<00:00, 623.84it/s]
                                                                                                                       
Copying val images for r:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for r:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  69%|██████████████████████████████████████████▏                  | 18/26 [00:03<00:01,  5.32it/s]
Copying train images for s:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for s:  87%|██████████████████████████████████████████████▏      | 61/70 [00:00<00:00, 593.76it/s]
                                                                                                                       
Copying val images for s:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for s:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  73%|████████████████████████████████████████████▌                | 19/26 [00:03<00:01,  4.85it/s]
Copying train images for t:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for t:  79%|█████████████████████████████████████████▋           | 55/70 [00:00<00:00, 533.49it/s]
                                                                                                                       
Copying val images for t:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for t:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  77%|██████████████████████████████████████████████▉              | 20/26 [00:03<00:01,  4.71it/s]
Copying train images for u:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for u:  97%|███████████████████████████████████████████████████▍ | 68/70 [00:00<00:00, 668.06it/s]
                                                                                                                       
Copying val images for u:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for u:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  81%|█████████████████████████████████████████████████▎           | 21/26 [00:03<00:01,  4.79it/s]
Copying train images for v:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for v:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for v:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  85%|███████████████████████████████████████████████████▌         | 22/26 [00:03<00:00,  5.20it/s]
Copying train images for w:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for w:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for w:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  88%|█████████████████████████████████████████████████████▉       | 23/26 [00:04<00:00,  4.95it/s]
Copying train images for x:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for x:  49%|█████████████████████████▋                           | 34/70 [00:00<00:00, 328.68it/s]
                                                                                                                       
Copying val images for x:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for x:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  92%|████████████████████████████████████████████████████████▎    | 24/26 [00:04<00:00,  4.38it/s]
Copying train images for y:   0%|                                                               | 0/70 [00:00<?, ?it/s]
Copying train images for y:  94%|█████████████████████████████████████████████████▉   | 66/70 [00:00<00:00, 642.28it/s]
                                                                                                                       
Copying val images for y:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for y:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase:  96%|██████████████████████████████████████████████████████████▋  | 25/26 [00:04<00:00,  4.51it/s]
Copying train images for z:   0%|                                                               | 0/70 [00:00<?, ?it/s]
                                                                                                                       
Copying val images for z:   0%|                                                                 | 0/15 [00:00<?, ?it/s]
                                                                                                                       
Copying test images for z:   0%|                                                                | 0/15 [00:00<?, ?it/s]
Splitting lowercase: 100%|█████████████████████████████████████████████████████████████| 26/26 [00:04<00:00,  5.36it/s]